MI

Mamba Codestral 7B v0.1

MistralGGUF by gabriellarsonUpdated 2025-07-03
Download on Hugging Face
Parameters7.29B
Context1024K
Layers64
Architecturemamba2
Smallest quant1.5 GB
Quick answer

Mamba Codestral 7B v0.1 needs about 4.1 GB of memory at IQ3_M (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 1.5 GB (IQ1_S) to 14.6 GB (F16).

Mamba Codestral 7B v0.1 – a code‑focused GGUF model

Mamba Codestral 7B v0.1 is a 7.29 billion‑parameter model based on the Mamba2 architecture. It is optimized for code generation and runs with the GGUF format via llama.cpp. The model is licensed under apache‑2.0.

Good at

  • Code completion
  • Debugging assistance
  • Script generation

Limits

  • No vision support
  • Large context required for full performance
  • Requires 8 k context for memory estimates

Best for

  • Developers needing lightweight code models
  • Educational coding tools
  • Rapid prototyping of scripts

Who it’s for. Engineers and hobbyists who want a fast, open‑source code model that can run locally. The model is suitable for developers who prefer a lightweight alternative to larger transformer‑based code models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 2.2 GB
Fits Get file →
IQ1_M1.7 GB 2.4 GB
Fits Get file →
IQ2_XXS2.0 GB 2.7 GB
Fits Get file →
IQ2_XS2.2 GB 2.9 GB
Fits Get file →
IQ2_S2.2 GB 3.0 GB
Fits Get file →
IQ2_M2.4 GB 3.2 GB
Fits Get file →
Q2_K2.5 GB 3.3 GB
Fits Get file →
IQ3_XXS2.9 GB 3.7 GB
Fits Get file →
IQ3_M3.2 GB 4.1 GB
Fits Get file →
Q3_K_M3.2 GB 4.1 GB
Fits Get file →
IQ4_XS3.9 GB 4.9 GB
Fits Get file →
IQ4_NL4.1 GB 5.1 GB
Fits Get file →
Q4_04.1 GB 5.1 GB
Fits Get file →
Q5_05.0 GB 6.1 GB
Fits Get file →
Q6_K6.0 GB 7.2 GB
Tight Get file →
Q8_07.8 GB 9.2 GB
Too big Get file →
F1614.6 GB 16.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.52 GB) or IQ1_M (1.69 GB). If you have 12 GB VRAM, IQ2_XS (2.18 GB) or IQ2_S (2.19 GB) provide a good balance of size and performance. For 16 GB VRAM, IQ3_M (3.2 GB) or Q3_K_M (3.2 GB) are recommended. All estimates are approximate.

What GPU do you need for Mamba Codestral 7B v0.1?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is IQ3_XXS (2.9 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_NL (4.1 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 9.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 9.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.6 GB file, about 16.8 GB in use).

Which Mamba Codestral 7B v0.1 quant should you choose?

IQ3_M (3.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 1.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemamba2
Parameters7.29B
Layers64
Trained context1,048,576 tokens

Source

Quantized bygabriellarson
FamilyMistral
Licenseapache-2.0
Downloads (HF)729
Last updated2025-07-03

Frequently asked questions about Mamba Codestral 7B v0.1

How much VRAM does Mamba Codestral 7B v0.1 need?

About 4.1 GB at IQ3_M with an 8K context window. That is the 3.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Mamba Codestral 7B v0.1 on an 8 GB GPU?

Yes, with Q6_K: the 6.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mamba Codestral 7B v0.1 GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 11 more.

What context length does Mamba Codestral 7B v0.1 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Mamba Codestral 7B v0.1 GGUF?

The files are on Hugging Face in the gabriellarson/Mamba-Codestral-7B-v0.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mamba Codestral 7B v0.1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Mamba Codestral 7B v0.1 on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantization files will fit within 8 GB VRAM with an estimated memory usage of 2.2–2.4 GB at 8 k context.

Does this model support image inputs?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Mamba-Codestral-7B-v0.1

Similar models

Browse all →

More from gabriellarson

All by gabriellarson →

More Mistral models

All Mistral →

Other small models

All small models →